Results 221 to 230 of about 98,329 (240)

BCAmirs at SemEval-2024 Task 4: Beyond Words: A Multimodal and Multilingual Exploration of Persuasion in Memes

International Workshop on Semantic Evaluation
Memes, combining text and images, frequently use metaphors to convey persuasive messages, shaping public opinion. Motivated by this, our team engaged in SemEval-2024 Task 4, a hierarchical multi-label classification task designed to identify rhetorical ...
Amirhossein Abaskohi, Amirhossein Dabiriaghdam, Lele Wang, Giuseppe Carenini   +3 more
semanticscholar   +1 more source

Persuasion strategies in medical media discourse: a functional and pragmatic analysis

Neophilology
INTRODUCTION. The relevance of the research is due to the need for a comprehensive study of the pragmatic aspect of communication in the media discourse of the modern medicine. The purpose of the study is to conduct a functional and pragmatic analysis of
G. N. Trofimova, M. V. Komleva
semanticscholar   +1 more source

Is Consumer Generated Branding the Way Forward for Digital Advertising: Examining the Effects of Message Source, Presentation Format and Involvement on Consumer Decisions on X (Formerly Twitter)

Journal of Current Issues & Research in Advertising
This empirical study compares the effects of consumer generated brand-related content versus brand generated advertising on X (formerly Twitter). Guided by the theory of planned behavior, elaboration likelihood model of persuasion, and media richness ...
V. Diwanji, Juliann Cortese, Jaejin Lee
semanticscholar   +1 more source

The Face of Persuasion: Analyzing Bias and Generating Culture-Aware Ads

Conference on Empirical Methods in Natural Language Processing
Text-to-image models are appealing for customizing visual advertisements and targeting specific populations. We investigate this potential by examining the demographic bias within ads for different ad topics, and the disparate level of persuasiveness ...
Aysan Aghazadeh, Adriana Kovashka
semanticscholar   +1 more source

Teacher engagement with automated text simplification for differentiated instruction

Language Learning & Technology
Differentiated instruction is much demanded yet quite challenging in face of the growing student diversity in today’s K-12 classrooms. One major challenge is the provision of differentiated materials to students. Automated text simplification (ATS) tools
Fengkai Liu, Yishi Jiang, Chun Lai, Tan Jin   +3 more
semanticscholar   +1 more source

Lies, Damned Lies, and Distributional Language Statistics: Persuasion and Deception with Large Language Models

arXiv.org
Large Language Models (LLMs) can generate content that is as persuasive as human-written text and appear capable of selectively producing deceptive outputs.
Cameron R. Jones, Benjamin K. Bergen
semanticscholar   +1 more source

Cyclic Vision-Language Manipulator: Towards Reliable and Fine-Grained Image Interpretation for Automated Report Generation

International Joint Conference on Artificial Intelligence
Despite significant advancements in automated report generation, the opaqueness of text interpretability continues to cast doubt on the reliability of the content produced.
Yingying Fang, Zihao Jin, Shaojie Guo, Jinda Liu, Zhiling Yue, Yijian Gao, Junzhi Ning (Raymond) Ning, Zhi Li, Simon L. F. Walsh, Guang Yang   +9 more
semanticscholar   +1 more source

The Duality of Persuasion: Between Personalization and Detection

The Web Conference
This PhD project investigates the duality of artificial intelligence in persuasive communication, exploring both the generation of personalized content and the detection of persuasive strategies. Insights are drawn from four studies.
Elyas Meguellati
semanticscholar   +1 more source

Ethics and Persuasion in Reinforcement Learning from Human Feedback: A Procedural Rhetorical Approach

Ethics: An International Journal of Social, Political, and Legal Philosophy
Since 2022, versions of generative AI chatbots such as ChatGPT and Claude have been trained using a specialized technique called Reinforcement Learning from Human Feedback (RLHF) to fine-tune language model output using feedback from human annotators. As
Shannon Lodoen, Alexi Orchard
semanticscholar   +1 more source

Diffusion-Geo: A Two-Stage Controllable Text-To-Image Generative Model for Remote Sensing Scenarios

IEEE International Geoscience and Remote Sensing Symposium
Image generation is a crucial task to facilitate intelligent interpretation in remote sensing domain. Expanding dataset size through image generation can enhance model performance of downtown task. However, current generative models in remote sensing are
Miaoxin Cai, Wei Zhang, Tong Zhang, Zhuang Yin, He Chen, Liang Chen, Can Li   +6 more
semanticscholar   +1 more source